Loading...

Optimal control of nonlinear dynamical systems using direct solution of neural network controllers

Pourtakdoust, S. H ; Sharif University of Technology | 2002

183 Viewed
  1. Type of Document: Article
  2. DOI: 10.2514/6.2002-4663
  3. Publisher: American Institute of Aeronautics and Astronautics Inc , 2002
  4. Abstract:
  5. Due to inherent potential of General Regression Neural Network(GRNN) to approximate nonlinear functions, it can be implemented as a nonlinear state-feedback controller. In this paper the methodology of direct collocation and nonlinear programming is utilized in combination with GRNN to determine the optimal control of dynamical systems. Application of this method to the design of an optimal controller for a chaotic flexible beam as a non-autonomous, nonlinear system is investigated. © 2002 The American Institute Aeronautics and Astronautics Inc. All rights reserved
  6. Keywords:
  7. Chaotic dynamics ; Grnn ; Neural networks ; Optimal control
  8. Source: AIAA Guidance, Navigation, and Control Conference and Exhibit 2002, Monterey, CA, 5 August 2002 through 8 August 2002 ; 2002 ; 9781563479786 (ISBN); 9781624101083 (ISBN)
  9. URL: https://arc.aiaa.org/doi/10.2514/6.2002-4663